science-of-finetuning
/

SAE-difference_bc-gemma-2-2b-L13-x32-k100-lr1e-04-local-shuffling

model_hub_mixin

pytorch_model_hub_mixin

Model card Files Files and versions

This model was trained on base_activations - chat_activations from gemma-2-2b

This model has been pushed to the Hub using the PytorchModelHubMixin integration:

Library: https://github.com/science-of-finetuning/dictionary_learning/
Docs: [More Information Needed]

Downloads last month: 3

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including science-of-finetuning/SAE-difference_bc-gemma-2-2b-L13-x32-k100-lr1e-04-local-shuffling

BatchTopK gemma-2-2b chat SAEs

Collection of SAEs we trained • 3 items • Updated Jun 5